[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: patient-time in Survival Analysis

From   "Carlo Lazzaro" <>
To   <>
Subject   st: patient-time in Survival Analysis
Date   Sat, 4 Aug 2007 09:11:49 +0200

Dear Statalisters,

I would kindly ask You for Your opinion about he folowing issue:

_ I am dealing with a 25-year open-cohort epidemiological model aimed at
comparing 2 different treatment (prevention = group A; therapy = group B;

- each year a 2,ooo new patients feed the model up (that is, 2,000 patients
for 25 years=50,000 patient for A and for B, respectively);

- no deaths or lost are considered;

_ patients may (or may not) convert to a X diseases during the 25-year

- aims of the model: 
--calculate difference in terms of cases of disease X for A and B;
--cost and Quality-Adjusted Life Years (QALYs) (see Drummond et al. Economic
Evaluation of Health Care Programmes. 3rd edition. Oxford: Oxford University
Press, 2006) for each patient enrolled in A and B from the date of enrolment
to the end of the model (that is until the 25th year);

_ no matter when patient converts (or doesn't convert)costs and QALYs
accrued for each patient are calculated until the 25 year (that is, until
the end of the model);

- my problem: since patient enter in the model in different years, I would
think to calculate with Stata 9/2 st function the person-time and the
following IRR for disease X for treatment A and B. 
However, I am not sure what is the right time person-calculation. Is it
(date of conversion -date of enrolment, if conversion occurs) or is it (25th
year of the model-date of enrolment)??

Any hints would be highly appreciated. Thanks a lot for Your Kindness and
for Your Time.

Kind Regards,


*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index